Voice function control method and apparatus

Patent metadata

Field	Value
Publication number	US-10991371-B2
Application number	US-202016820098-A
Country	US
Kind code	B2
Filing date	Mar 16, 2020
Priority date	Mar 31, 2017
Publication date	Apr 27, 2021
Grant date	Apr 27, 2021

Abstract

A first recognition result of an input voice is generated, where the input voice is input by a user of a terminal, and the first recognition result is generated by a voice assistant of the terminal. An application of the terminal is determined based on the first recognition result, where the application provides a service, and the application is different from the voice assistant. The input voice is passed to the application, where the application performs voice recognition on the input voice to generate a second recognition result. The service is provided to the user based on the second recognition result.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
generating, by a voice assistant of a terminal, a first recognition result of an input voice, wherein the input voice is input by a user of the terminal;
determining, by the voice assistant, an application of the terminal based on the first recognition result, wherein the application provides a service, the application is different from the voice assistant, and determining the application of the terminal based on the first recognition result comprises:
determining the service that the user wants to use based on the first recognition result;
in response to determining the service, displaying a plurality of applications of the terminal, wherein each application of the plurality of applications provides the service and supports voice input; and
determining the application from the plurality of applications based on a user selection;

passing, by the voice assistant, the first recognition result and the input voice to the application;
generating, by the application, a second recognition result by performing voice recognition on the input voice passed to the application, wherein the second recognition result is more accurate than the first recognition result in providing the service; and
providing, by the application, the service to the user based on the second recognition result and the first recognition result.

2. The computer-implemented method of claim 1 , wherein a mapping relationship between services and applications is maintained in the terminal, and determining the application of the terminal based on the first recognition result comprises:
determining the service that the user wants to use based on the first recognition result; and
determining the application based on the service and the mapping relationship between services and applications.

3. The computer-implemented method of claim 2 , wherein at least one of:
the mapping relationship between services and applications is set by the user;
in the mapping relationship between services and applications, for each particular service, a corresponding application is an application that is most frequently used by the user for the particular service; or
the mapping relationship between services and applications is submitted by a particular application.

4. The computer-implemented method of claim 1 , wherein a mapping relationship between services and applications is maintained in the terminal, the mapping relationship between services and applications includes a mapping relationship between function keywords and applications, and determining the application of the terminal based on the first recognition result comprises:
extracting a function keyword from the first recognition result; and
determining the application based on the function keyword and the mapping relationship between function keywords and applications.

5. The computer-implemented method of claim 1 , wherein determining the application of the terminal based on the first recognition result comprises:
extracting an application name from the first recognition result; and
determining the application based on the application name.

6. The computer-implemented method of claim 1 , wherein the application performs voice recognition on the first recognition result and the input voice to generate the second recognition result.

7. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
generating, by a voice assistant of a terminal, a first recognition result of an input voice, wherein the input voice is input by a user of the terminal;
determining, by the voice assistant, an application of the terminal based on the first recognition result, wherein the application provides a service, the application is different from the voice assistant, and determining the application of the terminal based on the first recognition result comprises:
determining the service that the user wants to use based on the first recognition result;
in response to determining the service, displaying a plurality of applications of the terminal, wherein each application of the plurality of applications provides the service and supports voice input; and
determining the application from the plurality of applications based on a user selection;

passing, by the voice assistant, the first recognition result and the input voice to the application;
generating, by the application, a second recognition result by performing voice recognition on the input voice passed to the application, wherein the second recognition result is more accurate than the first recognition result in providing the service; and
providing, by the application, the service to the user based on the second recognition result and the first recognition result.

8. The non-transitory, computer-readable medium of claim 7 , wherein a mapping relationship between services and applications is maintained in the terminal, and determining the application of the terminal based on the first recognition result comprises:
determining the service that the user wants to use based on the first recognition result; and
determining the application based on the service and the mapping relationship between services and applications.

9. The non-transitory, computer-readable medium of claim 8 , wherein at least one of:
the mapping relationship between services and applications is set by the user;
in the mapping relationship between services and applications, for each particular service, a corresponding application is an application that is most frequently used by the user for the particular service; or
the mapping relationship between services and applications is submitted by a particular application.

10. The non-transitory, computer-readable medium of claim 7 , wherein a mapping relationship between services and applications is maintained in the terminal, the mapping relationship between services and applications includes a mapping relationship between function keywords and applications, and determining the application of the terminal based on the first recognition result comprises:
extracting a function keyword from the first recognition result; and
determining the application based on the function keyword and the mapping relationship between function keywords and applications.

11. The non-transitory, computer-readable medium of claim 7 , wherein determining the application of the terminal based on the first recognition result comprises:
extracting an application name from the first recognition result; and
determining the application based on the application name.

12. The non-transitory, computer-readable medium of claim 7 , wherein the application performs voice recognition on the first recognition result and the input voice to generate the second recognition result.

13. A computer-implemented system, comprising:
one or more computers; and
one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
generating, by a voice assistant of a terminal, a first recognition result of an input voice, wherein the input voice is input by a user of the terminal;
determining, by the voice assistant, an application of the terminal based on the first recognition result, wherein the application provides a service, the application is different from the voice assistant, and determining the application of the terminal based on the first recognition result

Assignees

• Advanced New Technologies Co Ltd

Inventors

• Pan Shen

Classifications

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G10L15/32

  Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L2015/228

  of application context · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title